• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

The Estimation of the Borrower's Creditworthiness By the Market Information

Student: Kutej Irina

Supervisor: Victor A Lapshin

Faculty: Faculty of Economic Sciences

Educational Programme: Bachelor

Year of Graduation: 2014

<p>Risk management plays an important role in the banking sector worldwide. Banks and other financial institutions receive thousands credit applications every day. The issued loans risk assessment is based on the one of the most successful combinations of statistics and operational researches - credit scoring. Credit scoring is a set of forecasting models and underlying techniques that help financial institutions in the issuing of loans. Using an effective credit scoring bank can reduce the cost of credit process and the expected risk connected with the bad credit, increase quality of the credit decision, save resources and to increase profitability.</p><p>Object of research &ndash; the estimation of the borrower&rsquo;s creditworthiness scoring models</p><p>Subject of research &ndash; the practical analysis of the most common models of the estimation of the borrower&rsquo;s creditworthiness:</p><p>&bull; The rating model presented by a skoring technique (Raiffeisenbank, Promsvyazbank);</p><p>&bull; Predictive model based on logit regression;</p><p>&bull; The qualitative model using the rule &quot;Six C&quot;;</p><p>&bull; Classification and regression trees.</p><p>Purpose of the study &mdash; to compare the effectiveness of different assessment methods, and also to estimate complex use of these methods and to choose the most effective.</p><p>Research problems:&nbsp;</p><p>&bull;&nbsp; to consider theoretical aspects of the main component of the credit market &ndash; techniques of the creditworthiness estimation;</p><p>&bull;&nbsp; to define concepts, the purposes and problems of these techniques application;</p><p>&bull;&nbsp; to allocate their common features and the main distinctions;</p><p>&bull;&nbsp; to carry out the practical analysis of these techniques;</p><p>&bull; to compare the received results in terms of quality and transparency of techniques assessment;</p><p>&bull;&nbsp; to develop recommendations about application of these techniques for the creditor.</p><p>For this research it is necessary to consider specific economic conditions of the country with a transitional economy which the Russian Federation is. It can be difficult access to working capital, legal restrictions, undeveloped infrastructure, high transaction expenses, and also high interest rates for the credits &ndash; all these parameters can affect the modeling reports on small business. Therefore a research problem was to find the best model which will be able to take the main features for credit scoring for small business in such specific environment.</p><p>As many researchers found both personal and the business aspects of small business affecting the credit scoring model, their conclusions will be considered in my set of variables. Data collection was carried out by selection of leading commercial banks of the Russian Federation in which there is information on the credit history of small business owners from the general data set.</p><p>The made experiments with quantitative and qualitative models of the borrower&rsquo;s credit rating estimation showed that maximum efficiency of results can be achieved by applying the decision tree model and the correct choice of the key variables to a set of parameters for small business. At the same time, rating models can have positive result for small business if despite of weak financial performance of the companies, banks would be interested in lending and would be willing to provide the necessary human resources for gathering information, analysis and decision-making on lending.</p><p>The combination of logistic regression or decisions trees in addition to rating scoring has good reasons to be used for the small business borrower&rsquo;s estimation in the Russian Federation. In an economic environment which becomes more and more difficult and competitive, using only one of the methods is not enough for effective credit risk assessment, therefore researchers constantly are in search of new algorithms.</p>

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses